Item Slam Patch 7.41f
Disperser

Disperser: best heroes by WPA

Disperser in patch 7.41f: WPA of the purchase on 12 heroes, by role and build slot, against the other items bought in the same slot. Highest WPA, still inconclusive: Anti-Mage core, 3rd item (+5.34 pp).

By hero and slot

WPA of the item against the other items bought in the same slot, in matches of every rank. Slots with fewer than 30 purchases are left out.

Hero Role Slot Purchases WPA 95% CI Verdict
Anti-MageCore3rd item101 (0.9%)+5.34+1.60 to +9.21Inconclusive
Anti-MageCore4th+ item656 (3.6%)+4.38+2.23 to +6.75Inconclusive
WindrangerCore3rd item39 (0.5%)+2.12−0.29 to +4.38Inconclusive
SlarkCore3rd item719 (4.9%)+1.86−0.69 to +4.23Inconclusive
SniperCore3rd item46 (1.2%)+1.64−2.98 to +5.75Inconclusive
Legion CommanderCore4th+ item38 (0.4%)+1.56−1.64 to +4.46Inconclusive
JuggernautCore3rd item245 (2.0%)+1.36−2.14 to +4.76Inconclusive
JuggernautCore2nd item31 (0.2%)+1.24−3.41 to +5.89Inconclusive
WindrangerCore4th+ item253 (2.8%)+1.21−0.78 to +3.58Inconclusive
SlarkCore4th+ item3,418 (12.4%)+0.49−0.40 to +1.58Inconclusive
SniperCore4th+ item88 (1.5%)+0.41−4.41 to +4.07Inconclusive
SvenCore4th+ item50 (0.1%)+0.38−4.38 to +4.53Inconclusive
LifestealerCore4th+ item57 (0.3%)−0.65−5.69 to +3.82Inconclusive
Drow RangerCore4th+ item219 (0.5%)−0.85−4.16 to +2.85Inconclusive
SlarkCore2nd item158 (0.9%)−0.89−4.89 to +2.69Inconclusive
Drow RangerCore2nd item40 (0.1%)−1.20−4.77 to +2.34Inconclusive
Drow RangerCore3rd item60 (0.2%)−1.47−5.52 to +2.22Inconclusive
Phantom LancerCore4th+ item482 (2.6%)−1.79−4.72 to +1.24Inconclusive
JuggernautCore4th+ item463 (1.8%)−1.93−4.59 to +0.98Inconclusive
LunaCore4th+ item83 (0.2%)−5.09−10.69 to −0.35Inconclusive
Dragon KnightCore4th+ item43 (0.1%)−5.10−11.14 to +0.55Inconclusive

How to read

What is WPA?

Win probability added: how much choosing an item changed the chance of winning, in percentage points, compared with what the hero usually buys in that same slot and situation. +1.0 means the choice won 1 percentage point more than the typical purchase. Unlike raw win rate, it accounts for the game state when the item was bought, so an item bought from ahead doesn't look good just because the game was already won.

Build slots

1st, 2nd, 3rd and 4th+ count completed items. Components that become another item in most matches (Perseverance, Dragon Lance, Kaya) do not take a slot: the item they build into does. Boots get a card of their own.

Confirmed or not

The ✓ Better or ✕ Worse badge only appears when the effect passes the false discovery control (10%) in both ways of measuring: at the start of the decision and at the moment of purchase. Without a badge, the sign of the WPA is a trend.

Where the data comes from

Ranked (All Pick) matches parsed by OpenDota in the current patch. One model estimates the chance of winning from the game state; another, the effect of each item at the time of the decision. It is association, not causation: the model sees the game, not who is playing.