When
The last 12 referral batches arrived at 26, 32, 31, 32, 28, 38, 28, 35, 22, 27, 37, and 36 days.
The average is 31 days, the median is 32. We see 28 twice as well as 32.
I believe the 22 day batch was a fluke so I’m not going to use it for the early time frame, I will instead use 26 as the earliest expected date (you can always subtract four days from my soonest date if you disagree). The longest expected is 38.
The soonest I would expect to see referrals arrive this month is Tuesday, January 6, the latest is Monday, January 19. The most likely arrival is Monday, January 12.
December 12th, 2008 at 8:24 am
Thanks RQ. You addressed the exact issue that was on my family’s mind.
December 12th, 2008 at 10:21 am
After almost 4 years in the process you would think I’d know the answer to this question… but what usually happens with referrals around Chinese New Year? How long does CCAA close and does that closure delay or skip a referral batch?
December 12th, 2008 at 10:40 am
meilismom,
I was told they close CCAA for the first week, but not the second week.
December 12th, 2008 at 11:44 am
Thanks!
December 12th, 2008 at 12:33 pm
We should be next (2/27/06) and for that I am thankful but we were just told that we must re-do all the I-600A paperwork and pay the fees again because we have timed out on the 18-month timeframe…I just broke down and cried…home study, medicals, police checks, financial forms, fingerprints for Homeland Security and for our State, reference letters, everything. Yes, the wait is intolerable, but re-doing and re-doing paperwork takes this whole process over the top. Something needs to change here, but I have no idea how or if that could ever be accomplished. I am truly sorry to be so negative at this moment. We will do whatever it takes to have our second daughter home with us soon…and I am confident that all of you will do whatever it takes as well.
December 12th, 2008 at 2:11 pm
Going away until after Christmas & wanted to wish all you the very best for the holidays and every happiness in the coming year – hope to see you in China before July 4! Thank you for being here. LID 3/26/06
December 12th, 2008 at 3:30 pm
tessmom~
Did you already apply for the free extension?
Jo-Anne
2/28/06 Next or Next to Next
December 12th, 2008 at 3:36 pm
tesmom –
or the free fingerprinting?
December 12th, 2008 at 4:19 pm
tessmom,
When you say “timed out” do you mean your paperwork has already expired?
December 12th, 2008 at 5:10 pm
Hi – Thanks for the comments…this is our second 18-month period in the system. No, our paperwork has not expired (12/23/08 is the expiration date)..this is our second round to re-do the paperwork so we already received the free fingerprinting and extension…our agency said we have to pay all the fees again.
December 12th, 2008 at 5:32 pm
but at least its the I600A and not the new Hague document!
December 12th, 2008 at 5:48 pm
fjm – you’re correct! Thanks.
December 12th, 2008 at 6:27 pm
Who knows what is going on!! I do think they’ll be earlier next month… I just think this month was unfortunately late!
Lee-Anne
LID 22FEB2006
December 12th, 2008 at 9:30 pm
Could someone please explain the RQ’s logic. For the last couple years, the CCAA has issued referrals once a month. Sometimes it’s late one month, sometimes it’s early the next. The number of days between referrals averages to about 30. If the CCAA gives referrals late one month, odds are that there will be fewer days until the next referrals. By contrast, if the CCAA gives referrals early one month, odds are that there will be more days until the next referrals.
The real question seems to be which day is the median day, and what is the standard deviation from that day.
I appreciate what the RQ is doing, and all the work it takes. I just don’t understand it.
December 12th, 2008 at 10:24 pm
JustWait,
I wish I could, but let me try to recall some statistics. Mean is the average. Mode is the middle most. Median is the one in the middle. Standard deviation and the curve, well I can’t remember how that variation works. The likelyhood that it will deviate by one or two days? I need help there.
2335332 Mean you add all and divide by how many (easy)
Median is 5?
Mode would be 3.
That’s as much as I can help and not sure if it is 100% correct. I took Malox the entire time I had statistics class. We called it sadistics. Anyone, please feel free to step in and correct me.
December 12th, 2008 at 11:36 pm
I think mean or mode would be equally useful. I just don’t get the RQ’s logic. Doesn’t the CCAA refer every month within a week or so of the beginning of the month? Going back to May ‘05, the only exception is the weird 10/8/08 partial batch. Other than that, we never get more than 10 days from the first. This month was referred on 12/11, and the next batch is likely to come between 12/21 and 1/11, so we likely have 10 to 31 days between the last referral and the next referral.
What am I missing?
December 12th, 2008 at 11:46 pm
Basically, it seems to me that it might make more sense to look at the calendar and then count days. RQ’s method is to count days and then look at the calendar.
Again, I appreciate her efforts and this site, but I don’t understand this.
December 14th, 2008 at 3:17 pm
I dont think you are missing anything JustWait. As you said RQ’s method for doing this prediction assumes that the CCAA does not have a monthly referral cycle per se and that each referral cycle is independent of the previous cycle(s).
If you believe that the CCAA does try to work on something approximating a monthly cycle then RQ’s approach is not going to be very accurate when you have a month like the past month wherereferrals were relatively late based on a monthly cycle.
December 14th, 2008 at 3:33 pm
This isn’t rocket science, don’t try to make it more difficult or more complicated than it is. I’m just telling when the likely earliest and latest dates are, and then giving the most likely date based on an average. There is nothing that says if it is earlier one month it will be later the next month. All I do is give the likely window that they’ll show up. Anyone could do it, it’s not hard, it’s not difficult, it’s not complicated. And I clearly show how I come to the dates I do. What is there to not understand?
December 14th, 2008 at 7:33 pm
JustWait and Windthrow are right. RumorQueen’s analysis assumes each period is independent. If you assume they try to do one a month, a late one is more likely to be followed by a shorter period. With this assumption, a histogram is a better predictor like JustWait says. Here is such a histogram for the last 24 months.
Days after Number of occurrences
the first of
the Month
-1 to 0 3
1 to 2 7
3 to 4 5
5 to 6 5
7 to 8 2
9 to 10 2
December 14th, 2008 at 7:37 pm
the ascii formatted table looked bad. here it is again below. This kind of analysis says simply that it is most likely to happen one to six days after the first of the month, independent of when the last match was.
Days after— Number of
the first of—occurrences
the Month—
-1 to 0——-3
1 to 2 ——-7
3 to 4 ——-5
5 to 6 ——-5
7 to 8 ——-2
9 to 10 ——2
December 14th, 2008 at 8:59 pm
That’s a really shortsighted way of looking at it. The CCAA sends them out about once a month, and over the long run the time of the months shifts around. Back in 2006 it would have been accurate to say batches came between the 25th and the end of the month. But then there was a shift and then they started coming slightly later (or earlier, depending on how you look at it, since it shifted to the beginning of the month instead of the end). A year or two from now it might be accurate to say they come between the 8 and 15th. Over the long run, the way I do it works the best, by looking at the number of days between batches and stating the min, max, and average with however the weekends fall taken into consideration.
December 14th, 2008 at 9:27 pm
I think Teddy’s method is a better predictor of what is going to happen in the next month, but thats just me.
December 14th, 2008 at 9:33 pm
We’ll find out soon enough. His way points to between the first and sixth, right? Mine says the soonest is likely to be the 6th, with the most likely being closer to the 12th.
December 14th, 2008 at 10:37 pm
teddy
I’m curious, could you develop a probability density function from your histogram and assign probabilities to each day off from the first of the month?
December 15th, 2008 at 9:55 am
actually, the table says it is most likely to fall between the second and the seventh day of the month. (one to six days after the first).
for the probability density, divide the number of occurrences by 24.
Days after—
the first of—probability
the Month—
-1 to 0——0.125
1 to 2 ——0.292
3 to 4 ——0.208
5 to 6 ——0.208
7 to 8 ——0.083
9 to 10 ——0.083
December 15th, 2008 at 11:16 am
So Teddy am I doing this right?
Looking at the prior 24 months, and setting the last day of each month as the integer 0, I’m getting a mean of 3.92 and a standard deviation of 3.17.
Then I plot it on a normal distribution curve with this calculator:.
http://davidmlane.com/hyperstat/z_table.html
And, I’m getting that there is a 56% chance it falls between the 2 and 7th next month and only a 2.7% chance we would see it go to the 10th or beyond.
December 15th, 2008 at 4:24 pm
RQ, because of the random nature of the referral dates, I’m not sure if just next month’s result we’ll be a very good indication of whose method is more accurate, but if you test Teddy’s method over the past 12 months, you’ll find his mean (the rolling twelve-month average day-of-the-month) tends to be a more accurate predictor than the mean based on the rolling twelve-month average duration between referrals. I hope that makes sense.
December 16th, 2008 at 12:07 am
arw,
I don’t think a normal distribution captures the skew and kurtosis that appears in the data.
December 16th, 2008 at 1:15 am
Is there a distribution function that comes to mind for a peaked curve like this?